© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7390
    Prev
    Next
    INDEX
    Explanations

    Java code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     поверну
    0.54
     );//
    0.53
     ہیں
    0.52
     ทั้ง
    0.52
     थी
    0.51
     تھیں
    0.51
    実は
    0.51
     endif
    0.51
    そう
    0.50
     Otherwise
    0.50
    POSITIVE LOGITS
     MO
    0.53
    VersionUID
    0.51
     gentamicin
    0.51
    \"");
    0.51
     Cornell
    0.51
    特定的
    0.50
    叒
    0.50
    、【
    0.48
     Crohn
    0.48
    用心
    0.48
    Activations Density 0.213%

    No Known Activations